© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 12735
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries about answers and their complexities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.52
    bolista
    -0.49
     tartalomajánló
    -0.47
    UnusedPrivate
    -0.47
    afficheront
    -0.46
    httphttps
    -0.46
    IsMutable
    -0.45
     CreateTagHelper
    -0.45
    transQ
    -0.44
    ThroughAttribute
    -0.43
    POSITIVE LOGITS
     answer
    3.64
     answers
    3.34
    answer
    3.02
     Answer
    2.92
     answered
    2.91
    Answer
    2.77
     answering
    2.75
     Answers
    2.72
    answers
    2.69
     ANSWER
    2.67
    Activations Density 1.068%

    No Known Activations